Zobrazeno 1 - 10
of 1 309
pro vyhledávání: '"Chen, Zeyu"'
Recent advancements in large language models (LLMs) have highlighted the risk of misuse, raising concerns about accurately detecting LLM-generated content. A viable solution for the detection problem is to inject imperceptible identifiers into LLMs,
Externí odkaz:
http://arxiv.org/abs/2405.14604
Autor:
Chen, Tianyi, Ding, Tianyu, Zhu, Zhihui, Chen, Zeyu, Wu, HsiangTao, Zharkov, Ilya, Liang, Luming
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm. This topic spans various techniques, from structured pruning to neural architecture search,
Externí odkaz:
http://arxiv.org/abs/2312.09411
Autor:
Liao, Weibin, Xiong, Haoyi, Wang, Qingzhong, Mo, Yan, Li, Xuhong, Liu, Yi, Chen, Zeyu, Huang, Siyu, Dou, Dejing
While self-supervised learning (SSL) algorithms have been widely used to pre-train deep models, few efforts [11] have been done to improve representation learning of X-ray image analysis with SSL pre-trained models. In this work, we study a novel sel
Externí odkaz:
http://arxiv.org/abs/2310.02000
Natural language understanding (NLU) is integral to various social media applications. However, existing NLU models rely heavily on context for semantic learning, resulting in compromised performance when faced with short and noisy social media conte
Externí odkaz:
http://arxiv.org/abs/2308.09985
In this paper, we present an efficient quantum compression method for identically prepared states with arbitrary dimentional.
Externí odkaz:
http://arxiv.org/abs/2307.12024
Publikováno v:
In: Qunatum Information & Computation, Vol.24, 2024,pp0267-0294
In this paper, we consider two versions of the Text Assembling problem. We are given a sequence of strings $s^1,\dots,s^n$ of total length $L$ that is a dictionary, and a string $t$ of length $m$ that is texts. The first version of the problem is ass
Externí odkaz:
http://arxiv.org/abs/2306.10572
Publikováno v:
Phys. Lett. A 481, 129030 (2023)
In this paper, we show that the minimal quantum discord over "cross-symmetric" state extensions is an entanglement monotone. In particular, we show that the minimal Bures distance of discord over cross-symmetric extensions is equivalent to the Bures
Externí odkaz:
http://arxiv.org/abs/2303.10389
In this paper, the design and experimental demonstration of a snapshot linear-Stokes imaging spectropolarimeter (SLSIS) is presented. The SLSIS, which is based on division-of-focal-plane polarimetry with four parallel linear polarization channels and
Externí odkaz:
http://hdl.handle.net/10150/622866
http://arizona.openrepository.com/arizona/handle/10150/622866
http://arizona.openrepository.com/arizona/handle/10150/622866
In this paper, the design, optimization and analysis of broadband full-Stokes polarimeters with immunity to both Poisson and Gaussian noise are presented. Different from the commonly-used optimization metrics such as, the condition number (CN), the e
Externí odkaz:
http://hdl.handle.net/10150/622954
http://arizona.openrepository.com/arizona/handle/10150/622954
http://arizona.openrepository.com/arizona/handle/10150/622954
Word embedding has become ubiquitous and is widely used in various natural language processing (NLP) tasks, such as web retrieval, web semantic analysis, and machine translation, and so on. Unfortunately, training the word embedding in a relatively l
Externí odkaz:
http://arxiv.org/abs/2301.04312